Search

Stroke is among the leading causes of death and disability worldwide. Approximately 20-25% of stroke survivors present severe disability, which is associated with increased mortality risk. Prognostication is inherent in the process of clinical decision-making. Machine learning (ML) methods have gained increasing popularity in the setting of biomedical research. The aim of this study was twofold: assessing the performance of ML tree-based algorithms for predicting three-year mortality model in 1207 stroke patients with severe disability who completed rehabilitation and comparing the performance of ML algorithms to that of a standard logistic regression. The logistic regression model achieved an area under the Receiver Operating Characteristics curve (AUC) of 0.745 and was well calibrated. At the optimal risk threshold, the model had an accuracy of 75.7%, a positive predictive value (PPV) of 33.9%, and a negative predictive value (NPV) of 91.0%. The ML algorithm outperformed the logistic regression model through the implementation of synthetic minority oversampling technique and the Random Forests, achieving an AUC of 0.928 and an accuracy of 86.3%. The PPV was 84.6% and the NPV 87.5%. This study introduced a step forward in the creation of standardisable tools for predicting health outcomes in individuals affected by stroke.

Pragmatic communication abilities refer to the capacity to use language in a social context. Despite evidence to the contrary, the left cerebral hemisphere of the majority of right handers has been considered exclusively specialized for control of language phonology, syntax and semantics, whereas the right hemisphere has been specialized for the control of language pragmatics. Many studies have shown the non-exclusivity of the left hemisphere for language skills. Communication deficits observed in these studies for patients with right hemisphere damage confirmed the necessity for integrity of the right hemisphere across a number of language components. The aim of this study is to investigate the specific role of the right and left hemispheres across several aspects of communication deficits, with particular attention given to the influence of these deficits on functional outcome. The second aim is to characterize possible correlations between pragmatic and other cognitive deficits. We evaluated 22 patients, 15 with left- and 7 with right-brain ischemic or hemorrhagic damage, using cognitive, pragmatic and language tests. We deployed the Right Hemisphere Language Battery–Santa Lucia and Montreal d'Evaluation de la Communication to assess pragmatic abilities. The results showed no statistically significant differences between patients with left- and right-brain damage, highlighting the importance of integration between the two hemispheres in the communication process. Multiple significant correlations were found between pragmatic abilities and cognitive tests assessing global cognitive functioning, pantomime expression and comprehension. Pragmatic deficits were also shown to correlate with functional cognitive outcome. It is important to assess pragmatic abilities in patients with cognitive deficits after both left and right stroke for tailoring neuropsychological intervention to mitigate pragmatic disabilities in functional outcomes. [ABSTRACT FROM AUTHOR]